© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1489
    Prev
    Next
    INDEX
    Explanations

    theorem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     رع
    -0.09
    tai
    -0.09
    ন্দর
    -0.08
     dome
    -0.08
    ట
    -0.08
     Tai
    -0.08
    ক্ষণ
    -0.08
     skies
    -0.08
     Gow
    -0.07
     spod
    -0.07
    POSITIVE LOGITS
     replicas
    0.08
     Replica
    0.08
     Aver
    0.08
     Fung
    0.08
     averaging
    0.08
     abre
    0.08
     vista
    0.07
    Replica
    0.07
     age
    0.07
    _RC
    0.07
    Activations Density 0.000%

    No Known Activations